AutoML Leaderboard

Best model	name	model_type	metric_type	metric_value	train_time
	1_Baseline	Baseline	auc	0.5	1.36
	2_DecisionTree	Decision Tree	auc	0.519481	12.35
	3_Linear	Linear	auc	0.559809	7.16
the best	4_Default_Xgboost	Xgboost	auc	0.622437	58.33
	5_Default_NeuralNetwork	Neural Network	auc	0.583903	4.09
	6_Default_RandomForest	Random Forest	auc	0.535031	14.64
	Ensemble	Ensemble	auc	0.622437	0.78

AutoML Performance

AutoML Performance Boxplot

Features Importance

Spearman Correlation of Models

Summary of 5_Default_NeuralNetwork

<< Go back

Neural Network

• n_jobs: -1
• dense_1_size: 32
• dense_2_size: 16
• learning_rate: 0.05
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

2.9 seconds

Metric details

	score	threshold
logloss	0.713423	nan
auc	0.583903	nan
f1	0.682464	0.374215
accuracy	0.568627	0.52678
precision	0.7	0.778995
recall	1	0.148961
mcc	0.180831	0.374215

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.713423	nan
auc	0.583903	nan
f1	0.607143	0.52678
accuracy	0.568627	0.52678
precision	0.56044	0.52678
recall	0.662338	0.52678
mcc	0.13853	0.52678

Confusion matrix (at threshold=0.52678)

	Predicted as C	Predicted as N
Labeled as C	36	40
Labeled as N	26	51

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of 1_Baseline

<< Go back

Baseline Classifier (Baseline)

• n_jobs: -1
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

0.4 seconds

Metric details

	score	threshold
logloss	0.693164	nan
auc	0.5	nan
f1	0.669565	0.449015
accuracy	0.503268	0.449015
precision	0.503268	0.449015
recall	1	0.449015
mcc	0	0.449015

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.693164	nan
auc	0.5	nan
f1	0.669565	0.449015
accuracy	0.503268	0.449015
precision	0.503268	0.449015
recall	1	0.449015
mcc	0	0.449015

Confusion matrix (at threshold=0.449015)

	Predicted as C	Predicted as N
Labeled as C	0	76
Labeled as N	0	77

Learning curves

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of Ensemble

<< Go back

Ensemble structure

Model	Weight
4_Default_Xgboost	1

Metric details

	score	threshold
logloss	0.679375	nan
auc	0.622437	nan
f1	0.673469	0.474164
accuracy	0.614379	0.503049
precision	0.857143	0.568181
recall	1	0.371206
mcc	0.230151	0.50418

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.679375	nan
auc	0.622437	nan
f1	0.609272	0.503049
accuracy	0.614379	0.503049
precision	0.621622	0.503049
recall	0.597403	0.503049
mcc	0.229099	0.503049

Confusion matrix (at threshold=0.503049)

	Predicted as C	Predicted as N
Labeled as C	48	28
Labeled as N	31	46

Learning curves

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of 2_DecisionTree

<< Go back

Decision Tree

• n_jobs: -1
• criterion: gini
• max_depth: 3
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

11.0 seconds

Metric details

	score	threshold
logloss	0.889368	nan
auc	0.519481	nan
f1	0.663717	0
accuracy	0.542484	0.385421
precision	0.571429	0.627753
recall	0.974026	0
mcc	0.114445	0.385421

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.889368	nan
auc	0.519481	nan
f1	0.663462	0.385421
accuracy	0.542484	0.385421
precision	0.526718	0.385421
recall	0.896104	0.385421
mcc	0.114445	0.385421

Confusion matrix (at threshold=0.385421)

	Predicted as C	Predicted as N
Labeled as C	14	62
Labeled as N	8	69

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back

Summary of 6_Default_RandomForest

<< Go back

Random Forest

• n_jobs: -1
• criterion: gini
• max_features: 0.9
• min_samples_split: 30
• max_depth: 4
• eval_metric_name: auc
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

13.3 seconds

Metric details

	score	threshold
logloss	0.7221	nan
auc	0.535031	nan
f1	0.669565	0.113565
accuracy	0.581699	0.502156
precision	0.574713	0.502156
recall	1	0.113565
mcc	0.164058	0.502156

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.7221	nan
auc	0.535031	nan
f1	0.609756	0.502156
accuracy	0.581699	0.502156
precision	0.574713	0.502156
recall	0.649351	0.502156
mcc	0.164058	0.502156

Confusion matrix (at threshold=0.502156)

	Predicted as C	Predicted as N
Labeled as C	39	37
Labeled as N	27	50

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back

Summary of 4_Default_Xgboost

<< Go back

Extreme Gradient Boosting (Xgboost)

• n_jobs: -1
• objective: binary:logistic
• eta: 0.075
• max_depth: 6
• min_child_weight: 1
• subsample: 1.0
• colsample_bytree: 1.0
• eval_metric: auc
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

57.0 seconds

Metric details

	score	threshold
logloss	0.679375	nan
auc	0.622437	nan
f1	0.673469	0.474164
accuracy	0.614379	0.503049
precision	0.857143	0.568181
recall	1	0.371206
mcc	0.230151	0.50418

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.679375	nan
auc	0.622437	nan
f1	0.609272	0.503049
accuracy	0.614379	0.503049
precision	0.621622	0.503049
recall	0.597403	0.503049
mcc	0.229099	0.503049

Confusion matrix (at threshold=0.503049)

	Predicted as C	Predicted as N
Labeled as C	48	28
Labeled as N	31	46

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back

Summary of 3_Linear

<< Go back

Logistic Regression (Linear)

• n_jobs: -1
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

5.8 seconds

Metric details

	score	threshold
logloss	0.834594	nan
auc	0.559809	nan
f1	0.669565	0.022978
accuracy	0.581699	0.467724
precision	0.666667	0.88009
recall	1	0.022978
mcc	0.163438	0.467724

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.834594	nan
auc	0.559809	nan
f1	0.6	0.467724
accuracy	0.581699	0.467724
precision	0.578313	0.467724
recall	0.623377	0.467724
mcc	0.163438	0.467724

Confusion matrix (at threshold=0.467724)

	Predicted as C	Predicted as N
Labeled as C	41	35
Labeled as N	29	48

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back